融合SBAS-InSAR和WaOA-LSTM的上海浦东国际机场沉降监测与预测

Settlement monitoring and prediction of Shanghai Pudong International Airport by integrating SBAS-InSAR and WaOA-LSTM

为了监测上海浦东国际机场(SPIA)的沉降现状并提高长短时记忆(LSTM)网络模型预测精度,本文基于短基线集合成孔径雷达干涉测量(SBAS-InSAR)技术和32景Sentinel-1A影像,获取了上海浦东国际机场2020年9月—2023年8月的时间序列沉降信息;构建了基于海象优化算法(WaOA)优化的WaOALSTM沉降预测模型,并将预测结果与合成孔径雷达干涉测量(InSAR)监测值进行对比分析。结果表明,上海浦东国际机场近三年最大沉降速率为-52.21 mm/a,最大累积沉降量达到-159.30 mm,沉降主要集中在填海区的二号、四号和五号跑道,其中五号跑道北部周围护岸区域及沿海堤坝区域最为严重;WaOA-LSTM模型预测值与监测真实值的均方根误差为2.63 mm,平均绝对误差为2.06 mm,相较于传统LSTM模型分别提升了52.87%和53.29%。研究结果为上海浦东国际机场的安全运营提供了参考。

In order to monitor the settlement status of Shanghai Pudong International Airport(SPIA)and improve the prediction accuracy of the long short-term memory(LSTM)model,this paper obtained the time-series settlement information of SPIA from September 2020 to August 2023 based on the small baseline subset-interferometric synthetic aperture radar(SBAS-InSAR)technique and 32-view Sentinel-1A images.The walrus optimization algorithm(WaOA)-LSTM settlement prediction model optimized based on WaOA was constructed,and the prediction results were compared with the InSAR monitoring values.The results show that the maximum settlement rate of SPIA in the past three years is−52.21 mm/a,and the maximum cumulative settlement reaches−159.30 mm.The settlement is mainly concentrated in the reclaimed area of runways No.2,4,and 5,among which the berm area around the northern part of runway No.5 and the coastal embankment area are the most serious.The root-mean-square error(RMSE)of the predicted value by the WaOALSTM model and the real monitoring value is 2.63 mm,and the mean absolute error(MAE)is 2.06 mm,which are 52.87%and 53.29%higher than those of the traditional LSTM model,respectively.The results of the study provide a reference for the safe operation of SPIA.